Papers

Modern imaging produces terabyte-scale segmentation volumes, assigning each voxel an object label. These categorical, boundary-sensitive and label-rich data underpin connectomics and other imaging-driven fields, yet their scale often forces interpretation through slices, approximate meshes or distributed workflows that obscure spatial context and voxel-level defects. Here we show that such volumes can be explored directly on commodity hardware with Volcanite, an open-source framework for dense-segmentation rendering. Combining compression-aware data handling, a Vulkan GPU backend and segmentation-specific rendering, Volcanite enables low-latency exploration without meshing or distributed infrastructure, including for unpublished, sensitive or proprietary data. Across multi-domain datasets, it preserves voxel labels, adds shadows and global illumination, and renders up to half a trillion voxels at 100 frames per second. By replacing lengthy preprocessing with direct inspection, Volcanite decouples hypothesis generation from data preparation and turns teravoxel label fields into interactive evidence for discovery, validation and cross-domain spatial analysis

RNA design aims to identify sequences that fold into specified secondary structures. Existing methods formulate the task as target-specific search or conditional generation. However, natural RNA evolution proceeds through sequence variation and selection, with compensatory substitutions, whereas these methods do not explicitly model this process. To address this limitation, we propose a two-stage framework comprising RNA Inverse-Folding Flow (RNA-IFlow) and RNA-IFlow-RL. RNA-IFlow uses structure-conditioned Dirichlet Flow Matching to model coordinated variation across the sequence, while RNA-IFlow-RL maps the learned flow to a pairing-preserving finite policy and refines it with thermodynamic feedback. Our framework achieves leading performance on multiple benchmarks, reaching 85.19% Pass@1 on Rfam-27. Further analyses reveal thermodynamic gains, policy dynamics, and robustness across settings. Our work couples coordinated variation with thermodynamic selection, offering a novel paradigm for RNA design.

Speech brain-computer interfaces (BCIs) aim to restore communication by transforming neural activity related to speech, language, or communicative intent into external outputs such as text, synthesized voice, or avatar control. Recent advances in intracortical and electrocorticographic recording, deep sequence models, and language-model-assisted decoding have enabled rapid progress, including high-performance attempted-speech decoding and increasingly naturalistic speech synthesis. Yet these achievements also reveal that speech BCIs are not simply neural-to-text decoders. They are adaptive clinical systems in which neural representations, recording hardware, decoding architectures, language priors, feedback, and user learning interact over time. Here, we synthesize speech BCI research from a system-level perspective. We first examine the neural substrates of speech and language, emphasizing their hierarchical, distributed, temporally structured, and non-stationary organization. We then examine recording and decoding choices, closed-loop adaptation, evaluation, clinical translation, and ethics. Across these domains, we highlight recurring trade-offs between signal resolution and invasiveness, low-level motor and high-level semantic targets, decoder accuracy and user agency, and language-model fluency and faithful neural evidence. We argue the next generation of speech BCIs should be evaluated not only by offline accuracy, but also by robustness across sessions, calibration burden, latency, uncertainty, usability, and safeguards against unintended decoding. By reframing speech BCIs as adaptive, user-centred systems, we outline the interdisciplinary priorities spanning speech neuroscience, neural engineering, machine learning, clinical practice, and neuroethics needed to move from proof-of-concept decoding toward reliable, expressive, and controllable communication neuroprostheses.

Structural reasoning, the ability to recognize and make inferences over the relational structure between objects and concepts, is a hallmark of human cognition, yet prevailing methods often collapse relational topology into flat embeddings, cannot discover hidden structure and lack interpretability. We introduce Neural Structural Reasoner (NSR), a brain-inspired network that preserves relational structure directly in the connectivity and dynamics of coupled neuronal populations. NSR draws inspiration from three biological mechanisms: multi-layered architecture for encoding hierarchical knowledge, stable representations of entity and concepts, and path integration for input-driven state inference. At query time, NSR parallelizes computation over candidate relational structures and leverages confidence-weighted scores to perform link prediction. Across standard knowledge-graph benchmarks, NSR achieves competitive accuracy without leading on every dataset, and has lower reported training times than several neural baselines. Because reasoning is implemented through sequences of human-readable neuron activations, NSR affords native interpretability by tracking intermediate inference steps. The model further extracts latent relational hierarchies and compositional rules, demonstrating the brain-inspired architecture as an effective, efficient, and highly interpretable substrate for structural reasoning.

A common assumption in language model development is that cognitive abilities are organized around a general, domain-free intelligence factor, like fluid intelligence in humans. This assumption is rarely tested directly, and prior attempts have done so only at a much smaller scale. We take a latent variable approach to intelligence in language models, similar to how psychometricians study psychological constructs. Performance in every specific problem set is influenced by a domain-specific and a domain-agnostic latent factor. Using factor analysis as a dimension-reduction technique, we analyzed 13,251 published evaluation scores covering 1,618 language models across 456 different text-only benchmarks. Due to the super-sparse nature of the dataset, we triangulate our analysis across different data densifiers and imputation methods. A robust pattern across different modes of bias is that 1. A general intelligence factor accounts for 70.8% of variance in model performance at our most generous estimate, and far less than that in most of our solutions, 2. Content-similar benchmarks do not necessarily cluster together, and 3. The $g$ factor is not dominated by any common theme, and there is a lack of evidence that it is well-proxied by standard "intelligence" benchmarks. Our findings go against current endeavors of defining, identifying, and targeting general intelligence as a tangible construct in language model development. This leaves the strategy of targeting a single conceptual ability without support, since the first-order abilities it would have to reach are often partially idiosyncratic and not identifiable in practice.

Truncus arteriosus (TA) is a rare, severe congenital heart disease in which the two main arteries exiting the heart fail to separate in utero resulting in one truncus and truncal valve, carrying mixed oxygenated and deoxygenated blood. About 25% of patients have a quadricuspid valve, which is prone to regurgitation and re-intervention. Despite its relevance for valve performance and mixing, fluid mechanics in TA are poorly understood. Patient-specific fluid-structure interaction simulations were performed based on CT imaging before and after TA repair. The quadricuspid valve was constructed using elasticity-based design with the patient's free edge length and geometric height extracted from echocardiography. Interaction between blood and valve was simulated with the Immersed Boundary Method. Boundary conditions were tuned to the patient's data. Mixing of oxygenated and deoxygenated blood and streaming were assessed via Lagrangian Coherent Structures (LCS) and Lagrangian Particle Tracing (LPT). Low pressures, forward flow and streamwise vortices in the one-sided pulmonary arteries (PAs) throughout the cardiac cycle affected leaflet motion, leading to asymmetric closure and regurgitation. Holodiastolic aortic flow reversal supplied PA flow and the regurgitant jet. LCS and LPT indicated favorable streaming of oxygenated blood from the LV to the aorta and deoxygenated blood from the RV to the PAs. After truncal surgery, normal hemodynamics were restored. This is the first study of fluid mechanics of TA. Using qualitative and quantitative flow analysis, we identified disrupted preoperative hemodynamics caused by one-sided PAs and showed how normal hemodynamics were re-established after repair. Favorable streaming was demonstrated aligned with patient reports. Thus, favorable streaming is plausible in total mixing lesions and patient-specific modeling may aid in its detection.

Generative models make molecular crystal structure prediction fast, but their samples still exhibit geometric and packing violations. Physics can be introduced during training, post-training, or inference, yet these choices are rarely compared with the generator and physical signal held fixed. We introduce CrystAF, an all-atom crystal flow-map generation model, and use it with the UMA interatomic potential to systematically study where physics should enter. Post-training learns physical preferences directly into CrystAF, improving molecular validity and crystal packing while leaving sampling unchanged: physics is paid for once during training rather than repeatedly at deployment. In contrast, UMA relaxation is effective at repairing local clashes but makes generation 6–26$\times$ slower, while learning from relaxed targets provides little benefit. These routes are complementary rather than competing. Physics-informed post-training first shifts the generated distribution toward more physically reasonable structures, after which inexpensive inference-time corrections further remove clashes and restore stereochemistry that the generator cannot represent. Importantly, the same post-training strategy also improves the multi-step all-atom Clari-M and rigid-body MolCrystalFlow generators, demonstrating transfer across architectures and representations. Together, our results suggest a simple principle: learn reusable physical alignment into the generator, and reserve inference-time physics for residual constraints that are better corrected than learned.

An ongoing challenge in sensory neuroscience is to characterize the feature dimensions encoded by cortical populations. Recent approaches probe feature selectivity in a data-driven way, by synthesizing a most-exciting-input (MEI) for a target neural population. While this approach has been successfully applied to human higher visual cortex using fMRI data, generating MEIs for early- and mid-level retinotopic visual areas requires additional modeling constraints due to small receptive field sizes. To address this challenge, we introduce two novel MEI generation frameworks, Receptive Field Diffusion for Visual Exploration (RF-DiVE) and Receptive Field Gradient Optimization (RF-GO). Both methods use a population receptive field (pRF)-constrained voxelwise encoding model; RF-DiVE combines this with a pretrained latent diffusion model, while RF-GO uses regularized gradient ascent. When applied to single voxels in retinotopically defined areas V1-hV4, using data from the Natural Scenes Dataset, we obtain MEIs that exhibit consistent structure within the pRF, suggesting selectivity for local features like contour, color, and texture. We systematically compare MEIs generated by RF-DiVE and RF-GO using two encoding backbones, performing in-silico validation of predicted responses to MEIs using independent encoding models. Across all methods and all visual areas, MEIs elicit higher model-predicted responses than the most activating natural images. We further find that the choice of generation framework and encoding backbone differentially affects MEI properties, including their visual appearance, structural interpretability, and cross-model generalizability. These results offer a new approach for performing data-driven characterization of spatial and feature selectivity across human visual cortex.

Understanding how the brain parses actions and events from time-varying natural inputs is a central challenge in neuroscience. Recent work has used deep neural network (DNN) models to build stimulus-computable fMRI encoding models that predict single-voxel responses to complex natural videos. However, the majority of video-computable encoding models predict responses using simple linear mappings from model tokens, overlooking the spatiotemporal structure shared by video representations and neural responses. Recent cross-attention encoding models address this limitation for static images, enabling flexible stimulus-dependent weighting of image content across space. Here, we extend this framework to naturalistic video, using per-parcel cross-attention to dynamically route features from a self-supervised video model (V-JEPA-2) across both space and time, fitting this model to fMRI responses to short video clips. We compare joint spatiotemporal attention with factorized and selectively constrained alternatives, and find that joint routing improves predictions of brain responses to held-out videos across higher visual regions, most consistently in lateral and dorsal visual areas associated with dynamic motion perception. Moreover, our method provides interpretable, stimulus-specific attention maps that dynamically follow moving objects, revealing which locations and temporal moments contribute to each neural response. We further show that attention maps from parcels in different category-selective networks (face-, body-, scene-selective) differentially weight content in accordance with expected semantic selectivity. Together, this work provides a new computational framework for understanding how visual information is adaptively weighted by cortical populations during dynamic visual perception.

Deep learning models have achieved strong performance in artificial intelligence for science, yet their black-box nature limits our understanding of how they learn scientific tasks. Existing methods for interpretability provide limited insight into how models organize evidence and evolve during learning. We introduce explainability from training (EFT), a model-agnostic paradigm that traces model interpretation during training to explain why models rely on specific features and how they organize these features as predictive evidence. We apply EFT to four state-of-the-art T cell receptor (TCR)-epitope prediction models, TCR-SRIM, TULIP, MixTCRpred, and NetTCR-2.2, spanning post-hoc and interpret-by-design approaches as well as transformers and CNNs. To investigate how structural information affects model explanations, we introduce a benchmark, TCR-XAI2, containing 388 unique experimentally resolved TCR-epitope structures, complemented by structures predicted using AlphaFold3, Boltz-2, TCRModel2, tFold-TCR, and OpenFold3. Using EFT with TCR-XAI2, we demonstrate that (1) CNN and transformer models exhibit distinct learning trajectories; (2) TCR $\alpha$ and $\beta$ evidence can conflict during learning, limiting the benefits of jointly modeling both chains, while MHC information mitigates this; and (3) real versus predicted structural data for TCR-epitope prediction exhibits distinct TCR and peptide feature preferences as well as differing trajectories of model certainty.

Protein abundance alone does not capture the molecular diversity generated by protein processing and post-translational modification, yet most single-cell protein assays do not resolve these proteoform states. Here, we develop RCAmp-scWB, a post-separation amplification strategy that performs rolling-circle amplification directly within the polyacrylamide gel after single-cell protein electrophoresis. Reaction-transport modeling identifies a balance between reagent access and confinement of the template-associated amplification product that supports signal amplification while retaining the electrophoretically encoded spatial readout. Using purified protein standards, RCAmp-scWB produced a 4.0-7.8-fold steeper concentration-response slope than conventional single-cell western blotting. Across six human cancer cell lines, RCAmp-scWB quantified protein abundance and resolved distinct Vimentin and PD-L1 proteoform states whose relative abundance and single-cell distributions were not captured by total protein measurements alone. Extension to individual small extracellular vesicles further revealed source-dependent shifts in Vimentin proteoform composition despite comparatively similar abundance of one major Vimentin species. By separating electrophoretic molecular discrimination from signal amplification, RCAmp-scWB enables proteoform-resolved analysis of heterogeneous cells and small extracellular vesicles.

Collective patch-foraging experiments in the laboratory provide a controlled setting in which social information use can be quantified. Here, we consider a go/no-go task in which groups choose between two patches differing in food reward probability. We use agent-based simulations, underpinned by an augmented collective drift-diffusion model, to investigate alternative mechanisms for representing and integrating social information. We consider two representations, continuous (counting representation) and discrete (pulsatile representation), and two integration mechanisms, biasing the decision threshold (threshold modulation) and modifying the accumulated belief (belief modulation), yielding four distinct social models, in addition to a non-interacting model. We first characterize the collective dynamics generated by these models across cognitive parameters and experimental conditions. The temporal dynamics of group accuracy provide informative signatures of the underlying mechanisms. We then assess model selection and parameter identifiability using Bayesian inference and Wasserstein distance minimization, applied to group-accuracy and departure-time distributions. Bayesian inference using distributions of group accuracy provides the most reliable identification across the conditions considered. Importantly, model selection and parameter identifiability are associated with different aspects of collective behavior: model selection is closely linked to the presence of oscillations in the temporal dynamics, whereas parameter identifiability is more closely related to the global accuracy value. Thus, the information available for distinguishing the underlying cognitive mechanisms is not necessarily the same as that required to recover their parameters. Our results further show that identification depends not only on model structure but also on the experimental conditions.

Using predictive models to explain cognition requires more than accurate behavioral predictions. Input ablations offer an appealing route: remove information from a model and interpret the resulting performance change as evidence of its importance for behavior. Yet this inference assumes that the model's dependence on information reflects the dependence of the process generating the behavior. We test it in two synthetic sequential bandit tasks with known generating policies, where past choices can remain informative when feedback is unavailable to a predictor. We compare GRUs and Transformers trained from scratch, a fine-tuned LLaMA model, and cognitive models across systematically varied reward contributions. Our analyses distinguish prediction after training without reward observations from the response of a fixed predictor to donor-reward replacement. Three findings emerge. First, in the restless task, neural models trained without rewards predict held-out choices better than four simple training-fitted behavioral baselines. Second, under matched donor replacement, accurate predictors can respond much less than the known generator. Third, at some reward weights, neural networks predict better than a pooled reinforcement-learning model but have less faithful changes in choice probabilities; the model ordering differs between the two tasks. These independent-test results separate information sufficient for prediction from response fidelity under a specified ablation in sequential choice. They motivate validating model-ablation responses independently of predictive performance before using them to infer how the observed behavior was generated.

D-peptides combine protease resistance with high target specificity, but computational design of D-peptide binders remains immature. Mirror-Peptidizer introduced an in silico mirror-image screening pipeline using target reflection, backbone generation, and ProteinMPNN sequence design, but its raw ProteinMPNN negative log-likelihood (NLL) ranking was not validated against measured affinities, and only 4 of 9 tested MDM2 designs bound detectably. We introduce Mirror-Score, a calibrated, inference-only scoring framework for heterochiral D-peptide/L-protein complexes, and a public benchmark of 31 crystal complexes across four target families, including 18 with literature-verified affinities. Raw ProteinMPNN NLL is not a valid affinity ranker: its pooled Spearman correlation with affinity is 0.19, and correlations reverse between MDM2/CHIP (+0.62) and gp41 (-0.70). We therefore evaluate Boltz-2 mirror-space cofolding confidence. For the complete viral-entry family (7 structures representing 3 peptides), interface predicted local distance difference test (pLDDT) achieves structure-level leave-one-out Spearman rho = 0.90 (p = 0.006) and correctly orders all three peptides by affinity, whereas NLL fails (structure-level rho = 0.18). Because only three independent chemotypes are represented, this result indicates directional consistency rather than a statistically validated predictor. Cross-family calibration does not transfer at current sample sizes, supporting family-matched calibration as the practical deployment mode. We also specify a prospective design protocol for the antimicrobial-resistance targets LasR and LecB from Pseudomonas aeruginosa, including mirrored structures, ligand-derived hotspot maps, diffusion-model-ready inputs, and Mirror-Score ranking. Code, benchmark data, structures, and analysis scripts are openly available at https://github.com/Jiadalee/Mirror-Score.

The dynamics of adaptation in a population are informed by its mode of reproduction. Whether individuals reproduce sexually or asexually, then, can have large effects on population persistence and extinction in changing environments. Classical theory explains this dependence via genetic variance without further accounting for a fundamentally different mode of inheritance. Recent theoretical advances capture these mechanisms, highlighting how they dramatically change the nature of adaptation in gradually changing environments. Here we show that these recent predictions, which assume infinite-population sizes, are overly optimistic about the fate of finite asexual populations when environmental change is rapid. This is because every individual in an infinite asexual population descends from a once optimal ancestor and the likelihood of finding this optimal individual in the population declines rapidly with population size. To predict the fate of finite asexual populations we derive the equilibrium phenotypic distribution assuming there exist no individuals beyond some unknown trait. As expected, we find that when the phenotypic distribution contains the optimal trait, the population's fate is consistent with previous predictions. When the optimal trait is lost, however, an additional fitness load is incurred. We further derive a prediction for the typical trajectory of an ancestral lineage, which explains the additional load: all individuals descend from a common ancestor carrying the fittest trait, which may be suboptimal. Our work uncovers a finite-population effect that is specific to asexual adaptation and distinct from genetic drift, which significantly hinders the ability of small asexual populations to persist in changing environments.

Bacteriophage Q$\beta$, first isolated in 1961, has served for more than six decades as a model system for molecular and viral evolution. The development of cell-free replication systems based on the Q$\beta$ replicase enabled the first demonstrations of Darwinian evolution in RNA molecules. In parallel, the phage's compact RNA genome, high mutation rate, and ease of propagation established Q$\beta$ as an exceptionally tractable model for studying viral evolution. The discovery of extensive genetic heterogeneity made of Q$\beta$ the first biological system in which molecular quasispecies theory found direct experimental support. Building on this foundation, decades of evolution experiments under thermal, ecological, and mutagenic pressures established how mutation, selection, epistasis, and population structure jointly shape adaptive trajectories. Deep sequencing has recently allowed the mutant spectrum of Q$\beta$ populations to be resolved as large, structured genotype networks, revealing a hierarchical organization around dominant sequences that generalizes classical mutation-selection balance to a dynamic process, and uncovering topological features shared with RNA viruses evolving within natural hosts. In parallel, the catalytic core of the Q$\beta$ replication system has been repurposed in synthetic biology to revive cell-free Darwinian evolution within compartmentalized, cell-like systems, opening new avenues for studying the origin and early evolution of life. Further recent work has pushed the phage into new experimental territories, including extreme, astrobiologically relevant environments and biotechnological platforms for peptide display. Together, these developments illustrate how a single bacteriophage has repeatedly anticipated and continues to clarify general principles of molecular, population, and ecological evolution.

Effective central nervous system (CNS) intervention requires more than predicting biological responses: a scientific system must determine which intervention, observation, or additional evidence can improve a decision under uncertainty. However, in partially observed neuronal microenvironments, identical predicted outcomes may correspond to different exposure states, biological mechanisms, and intervention risks. We propose NeuronSifter, a decision-centric Agent-in-Twin framework, where an AI agent operates with an evolving biological digital twin rather than a fixed predictive model. NeuronSifter compiles interventions into state-conditional target-occupancy representations, propagates them through a mechanism-grounded World Action Model (WAM), and selects informative measurements based on their expected reduction in decision uncertainty. A shared probabilistic belief state couples intervention simulation, observation selection, and outcome assimilation, enabling the digital twin to continuously refine its decision-relevant representations through externally verified evidence. We evaluate NeuronSifter in Alzheimer's disease intervention scenarios using mechanistic neuronal microenvironment simulations and retrospective clinical endpoint references. The evaluation framework examines adaptive evidence acquisition, uncertainty-aware intervention planning, and robustness under model discrepancy through controlled environments and independent comparisons. NeuronSifter demonstrates how an AI system can actively identify missing evidence, refine biological hypotheses, and optimize intervention decisions under limited experimental budgets. Code is available at https://anonymous.4open.science/r/NeuronSifter.

Quantitative characterization of lymph node morphology is important for assessing axillary lymph node metastasis in breast cancer. However, surfaces reconstructed from computed tomography (CT) segmentation may contain geometric and topological defects that compromise subsequent analysis, while conventional shape descriptors predominantly characterize global morphology. To address these issues, we developed an integrated framework combining topology-aware surface processing with multi-resolution spherical harmonic (SH) analysis of CT-derived axillary lymph nodes. The processing pipeline produced topology-valid genus-0 surfaces with improved mesh quality, which were then represented at multiple SH degrees and characterized using 20 predefined geometric feature families. Geometric fidelity increased with SH degree, whereas predictive performance peaked at intermediate resolutions. Preferred SH degree also differed across feature families. A family-specific mixed-resolution model achieved an AUC of 0.918, compared with 0.884 for the conventional PyRadiomics Shape14 baseline, corresponding to an improvement of 0.0344. Controlled perturbation experiments showed that higher SH degrees transmitted more fine-scale geometric variation and yielded lower stability of curvature-based predictions. Representative geometric descriptors provided interpretable characterization of metastasis-associated surface morphology. Independent validation further supported the framework's transportability: label-free replication in a multicenter lymph node cohort reproduced the family-specific resolution effects, while a labeled LIDC-IDRI lung-nodule experiment reproduced the resolution-dependent relationship between SH degree and predictive performance. Altogether, the framework provides a topology-valid basis for quantitative characterization of lymph node morphology and metastasis-associated imaging phenotypes.

Mechanistic discovery in neuronal microenvironments requires interventions and measurements that separate competing explanations of solute transport and neuronal response. Predictive accuracy cannot settle the question: a real mechanistic change and an error in the computational twin leave the same signature in sparse observations. We formalize this twin confounding and reason over a joint mechanism–discrepancy belief, designing experiments that separate the two. NeuronDiscover is an Agent-in-Twin framework whose shared, mechanism-grounded World Action Model (WAM) couples prediction, intervention proposals, and observation design; independently adjudicated outcomes revise a scoped Mechanism–Intervention–Observation–Outcome (MIOY) graph, whose supported relations compile into executable programs carrying discrepancy-adjusted acceptance bounds. We evaluate on simulated brain-fluid tracer-transport worlds adjudicated by an independently frozen finer-mesh reference solver, and on donor-disjoint public current-clamp recordings of cortical neurons. Counting only relations that reach a certified terminal status, and scoring abstentions as unresolved for every method, at a matched budget of 16 experiments over 32 source units NeuronDiscover resolves 4.0 relations per assigned world against 3.4 for the strongest baseline and 3.2 without graph revision, at 5% false support and 82% scope accuracy. Joint mechanism–discrepancy acquisition resolves 3.8 relations versus 2.9 for plug-in expected information gain; discrepancy-adjusted verification lowers accepted-program failure from 15% to 9% at 60% acceptance coverage; and transfer to the recordings yields 1.94 versus 1.53 relations per assigned world. Correctness is adjudicated within declared model worlds and archival recordings.

Cardiac model personalisation requires inferring mechanical parameters that are not directly measurable in vivo. Ultrafast ultrasound shear wave elastography (SWE) enables non-invasive tracking of myocardial stiffness dynamics over the cardiac cycle, providing a target for personalisation. However, mapping these observations to subject specific model parameters remains ill-posed, as multiple parameter sets can reproduce the same stiffness dynamics. We formulate SWE-informed personalisation as a statistical inference problem using simulation-based inference (SBI). Using a subject-adapted 0D cardiovascular model and neural posterior estimation, we estimate model-conditional posterior distributions over active stiffness scale k0, contraction rate kATP, and relaxation rate kSR, conditioned on SWE-derived curve features and subject specific context. Among six healthy volunteers, four passed objective prior-support diagnostics and were retained for quantitative posterior analysis. Curve-level RMSE against the observed SWE target decreased from 12.61 $\pm$ 5.55 kPa for the prior predictive median to 1.14 $\pm$ 0.38 kPa for the posterior predictive median, an 89.7 $\pm$ 4.2% reduction. Posterior analysis revealed parameter-specific uncertainty, k0-kATP compensation, weaker constraint of kSR, and the importance of prior-predictive diagnostics for assessing whether each subject is represented within the modelled SWE feature space. These results support SBI for uncertainty aware SWE-based personalisation, while identifying prior support and forward-model adequacy as key diagnostics.

A major challenge in neuroscience and machine learning is to connect single-neuron influence, population dynamics, and circuit connectivity in a causal account of computation. Much previous work has shown that low-rank connectivity can generate low-dimensional dynamics in trained artificial neural networks, but this leaves unclear the functional relevance of the higher-rank structure of biological neural circuits and many artificial neuronal networks. Here we analyse recurrent neural networks trained to locate rewards by integrating continuously varying speed inputs in one- and two-dimensional spatial tasks. We find that dominant low-dimensional dynamics encode task locations, and can be causally manipulated to instruct behavioural outcomes. However, after decomposing the underlying circuitry we found that while low-rank connectivity accounts for the low-dimensional dynamics, accurate performance and generalisation to novel speed distributions requires high-rank connectivity. We demonstrate that this is achieved through distributed signalling that corrects errors in low-dimensional location representations. Thus, combined perturbation-, representation-, and circuit-level analyses demonstrate a novel mechanism for robust spatial computation and show how high-rank connectivity in neural circuits can provide a scaffold that supports precision and generalisation.

Mass gathering events like concerts, sports matches, and festivals bring many people into close contact within a short period, creating localized bursts of infection that can shape epidemic outcomes across an entire city. To evaluate how these transient transmission events translate into broader urban impacts, we developed a simulation model linking event-scale contact dynamics with citywide commuting networks. Using Madrid, Spain, as a case study, we compared several types of gatherings and examined how their effects changed under different levels of disease transmissibility. We found that mass gatherings consistently amplified outbreak magnitude, accelerated progression, advanced district-level arrival times, and synchronized spatial spread. Remarkably, while the initial seed size generated at the event accounted for much of this acceleration, post-event transmission conditions provided complementary predictive signal regarding invasion timing. These findings demonstrate that mitigating transmission during mass gatherings can yield downstream public health benefits by delaying broader spatial spread. More generally, this multiscale framework offers a tool to evaluate how temporary, localized contact shifts produce longer-lasting consequences for urban populations.

We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from human populations. DoAtlas-2 integrates 771 research resources covering more than 720,000 participants in 48 countries, from longitudinal clinical phenotypes, medical imaging, and continuous physiological signals to eight molecular layers, together with an evidence network of approximately 4.7 million literature-derived records over 93,566 concepts and 149,383 candidate causal relations. DoAtlas-2 autonomously formulates research questions from evidence gaps and unresolved mechanisms, prespecifies their causal designs, and generates validated analyses. Supporting, challenging, and unresolved results continuously revise mechanistic interpretations, the causal evidence state, and the discovery frontier, so that DoAtlas-2 self-evolves within a closed loop of hypothesis generation, empirical testing, and renewed discovery. DoAtlas-2 has systematically evaluated 2,031 research questions. In the Human Phenotype Project (HPP), it formulated 4,014 candidate pathway questions across vascular, early-glycemic, and hepatic-metabolic systems, and screening of the first 1,079 yielded statistical support for 756. Representative studies identify blood pressure as a convergence node linking adiposity, hepatic, and lipid phenotypes to vascular outcomes, and show that an adiposity-inflammation-blood-pressure pathway is largely attenuated by joint adjustment for body mass index (BMI) and smoking. The discovered vascular network constitutes a completely interpretable predictive foundation, admitting exact attribution of every prediction and closed-form mediation effects. DoAtlas-2 thereby unifies causal mechanism discovery, population-evidence testing, and interpretable prediction within one continuously evolving foundation.

Biological machine learning was long bottlenecked by the ability to synthesize designed DNA. Variational synthesis models control chemical reactions to physically manufacture quadrillions of designed sequences in DNA. However, training these generative models is challenging: constraints on chemical synthesis can force many parameters into a discrete space, limiting the ability to pre-train and fine-tune. In this article we train “free” variational synthesis models using stochastic gradient descent in continuous space, and then discretize with post-training quantization to impose hardware and wetware constraints. This enables variational synthesis models to satisfy stringent reward criteria, while still synthesizing diverse designs, achieving a strictly dominating quality-diversity Pareto frontier. We demonstrate by training variational synthesis models of enzymes, peptides, antibody CDRH3s, and regulatory DNA elements. In silico performance is maintained in vitro.

Deep learning has become a cornerstone of EEG-based brain decoding, with a growing number of architectures proposed every day. However, how the performance of these different models scales with data volume is not clear. Although this relationship has been characterized in other fields under the name of scaling laws, it remains poorly understood in the EEG domain. The present study addresses this gap by investigating how scan time and subject diversity affect the performance of different architectures. We evaluated five models across four EEG datasets. Training data volume was controlled by varying both subject count and trial volume under cross-subject validation. We then fitted power-law relationships to characterize the resulting behavior. Our findings reveal that as total data volume increases, the distinction between trial and subject scaling becomes largely irrelevant. Furthermore, we show that power-law relationships are both model and dataset-specific, yet they provide a robust descriptive framework for EEG decoding performance. Extrapolation to larger subject pools yields RMSE values below 0.1 in most cases. Our work contributes to the literature by providing a descriptive framework for data scaling in EEG and by demonstrating data-efficient experimental design in EEG research.

Ecological fitting describes a situation where species interact despite no shared evolutionary history. It is both a null model for adaptation and an important process in its own right, for example, the establishment of a non-native species is ecological fitting, and it is a major mechanism in the formation of Novel Ecosystems. In this paper we introduce and analyse a model of ecological fitting. We demonstrate both analytically and through simulation that the main factors determining invasion success are the invaded ecosystem's population and diversity, which set the size of the barrier for invaders. We also study the situation where many evolutionarily unrelated species simultaneously colonise an empty area. We show that a successful equilibrium is likely to be established, but the diversity tends to be very much less than the number of species in the starting pool and discuss the implications of this.

Reliable decisions depend on recognizing when an answer may be wrong. In biological cognition, metacognitive monitoring can dissociate from task performance, raising the question of how closely solving and judging are linked in language models. Here we study the confidence reports of four frontier models across 15 benchmarks. High task accuracy can coexist with weak error discrimination: a model solves 97% of competition mathematics problems while its answer-time confidence ranks correct answers above errors barely better than chance. Confidence separates correct answers from errors more effectively on questions solved by a separate reference model, while review brings limited improvement on reference-hard questions. Aggregate discrimination also rewards ranking correct answers on easy questions above errors on hard ones, which question-only forecasts already do well. Cross-evaluation helps most where the evaluator answered correctly, and errors shared by the two models usually retain high confidence. Hard questions and shared errors remain difficult targets for prompted self-review and peer oversight, even in models with strong problem-solving performance.

Foundation models are increasingly adapted to individual users, but an apparent personalization gain can simply reflect a stronger population model. This distinction matters for brain-computer interfaces, where every new user must be calibrated. We evaluated personal adaptation of three frozen EEG foundation models (CBraMod, REVE and LaBraM) in 235 held-out subjects from three motor-imagery datasets, comparing each subject's adapter with the population model and with adapters fitted to other subjects. Using all first-half session labels, personal adapters improved mean balanced accuracy over the population model by 1.5-5.4 percentage points and outperformed exchanged adapters by 2.3-7.3 points in all nine model-dataset combinations. The size of this benefit depended on population training: with four times the original budget, median gains remained positive (1.0-2.0 points) but were smaller for every model, and no population model reached a confirmed plateau. Acquiring the benefit cheaply was unreliable: few-label calibration was consistently non-negative on only one dataset, and in CBraMod neither unlabeled context nor meta-learned initialization outperformed matched controls. Personalization should therefore be evaluated against both a population reference and exchanged parameters, across population-training budgets.

Accurate fitness prediction is central to protein engineering and understanding sequence-function relationships. With advances in deep learning, protein foundation models (PFMs) have become widely used for this task. Recent analyses, however, show that these models share preferences reflecting their training corpora, while unreliable inputs can further distort fitness predictions. Family-specific evolutionary evidence and structural context can help address these limitations by providing complementary constraints on model scores, motivating VenusREM-Harness (VRH), a general, model-agnostic, training-free Retrieval-Enhanced Mutation harness. It fuses frozen model scores with multiple sequence alignment (MSA) evidence according to model uncertainty, then applies gated background correction and score shrinkage based on structural confidence and solvent exposure. Across 1,211 assays and 3.1 million measured variants from ProteinGym, VenusMutHub, and the newly curated viral benchmark VenusViroHub, all 71 configurations improve Spearman correlation on all 3 benchmarks by 0.073 on average, with broad gains across 5 metrics. Extended analyses relate retrieval gains to model-MSA preference differences, assess domain-level gains and immune-escape cases, and quantify computational speedups. Built with VRH, VenusREM2 is the first to rank highest in all function, taxon, MSA-depth, and mutation-depth categories, with a ProteinGym Average Spearman of 0.556, 0.038 above the prior best.

Recent high-resolution (500 bp) Hi-C experiments reported contact maps with unusual patterns around highly expressed bacterial DNA loci. These patterns, described as arched stripes and bundled domains, extend over nearly 100 kbp. We performed Brownian Dynamics simulations with a specially designed coarse-grained model to rationalize these findings. The main feature of the model is that it takes explicitly into account the waves of positive (respectively, negative) supercoiling generated by the translocating polymerase downstream (respectively, upstream) of its position. Contact maps computed from the simulations also display the arched stripe and bundled domain patterns for above-threshold values of the rate of twist injection. Computed DNA conformations indicate that these patterns reflect an extraordinarily entangled DNA geometry, which involves both plectonemic and toroidal supercoiling, with some DNA segments experiencing both of them simultaneously. Moreover, DNA segments located on each side of the polymerase systematically wind around tracts located on the other side, which is a purely out-of-equilibrium effect driven by the continuous injection of twist. The present work therefore reveals that repeated transcription of a DNA locus systematically brings into contact DNA segments separated by several tens of kbp, which may eventually contribute to allosteric modulation and long-range communication.